SCH: INT: Mapping the Cardiac Acousteome: Biosensing and Computational Modeling Applied to Smart Diagnosis and Monitoring of Heart Conditions

该项目的目标是开发基于自动心脏听诊的智能诊断和监测心脏状况的基础科学、知识、工具和技术。提出了一种创新的可穿戴多模态声阵列（StethoVest）。该传感阵列通过测量声场的空间和时间导数来定位和分离空间中的声宽带源。使用这种听诊器，首次生成了心脏听体的地图。这些地图不仅包括对心音的4D（三维空间和时间）测量；它们伴随着高保真的血液声学模拟，描述了因果关系，以及模拟引导的源识别算法，提供了前所未有的诊断灵敏度和特异性。该模拟以心脏成像数据为输入，模拟心脏血流以及相关的心音。这个为期四年的项目的后半部分侧重于研究主动脉瓣杂音的物理特性以及基于听诊器的肥厚性阻塞性心肌病筛查。每年国家在心脏病方面的支出超过5000亿美元，每年有50多万人死于这种疾病。拟议的研究利用生物传感、计算建模、成像和信号处理方面的新兴能力，产生一种诊断技术，使我们摆脱主要是反应性、昂贵和以医院为中心的心脏病管理，转向一种智能、主动、以患者为中心和具有成本效益的方法。通过对心音的连续、自动监测和解读产生的声音清单有可能产生对人类生理学前所未有的理解。该项目通过让本科生、研究生和博士后参与研究、开发课程和临床培训工具，以及开展本地和国际推广活动，促进跨学科教育和劳动力发展。

The goal of the project is to develop fundamental science, knowledge, tools, and technologies for smart diagnosis and monitoring of heart conditions based on automated cardiac auscultation. An innovative wearable multimodal acoustic array (the StethoVest) is proposed. This sensory array localizes and separates acoustic broadband sources in space by measuring spatial and temporal derivatives of the acoustic field. Using this StethoVest, first-of-their-kind maps of the cardiac acousteome are generated. These maps include not only 4D (3D space and time) measurements of heart sounds; they are accompanied by high-fidelity hemoacoustic simulations that delineate cause-and-effect, as well as simulation-guided source-identification algorithms that provide unprecedented diagnostic sensitivity and specificity. The simulations take cardiac imaging data as input, and simulate cardiac blood flow as well as the associated heart sounds. The latter part of this four-year project focuses on investigating the physics of aortic valve murmurs as well as StethoVest based screening for hypertrophic obstructive cardiomyopathy. Annual national expenditure on heart disease exceeds half a trillion dollars with over half a million deaths attributed to this disease each year. The proposed research leverages emerging capabilities in biosensing, computational modeling, imaging and signal processing, to produce a diagnostic technology that moves us away from management of heart disease that is mostly reactive, expensive and hospital-centric, towards an approach that is smart, proactive, patient-centric and cost-effective. The sound inventory generated from continuous, automated monitoring and interpretation of heart sounds has the potential to generate unprecedented understanding of human physiology. The project promotes interdisciplinary education and workforce development through involvement of undergraduates, graduate students, and postdocs in the research, development of courses and clinical training tools, and local and international outreach activities.